Image: Qi et al
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Point cloud is an important type of geometric data structure.
Ranked #2 on Scene Segmentation on ScanNet
By exploiting metric space distances, our network is able to learn local features with increasing contextual scales.
Ranked #1 on Semantic Segmentation on S3DIS (Accuracy metric)
Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices.
Ranked #1 on 3D Point Cloud Classification on ModelNet40
With the massive data set presented in this paper, we aim at closing this data gap to help unleash the full potential of deep learning methods for 3D labelling tasks.
Specially, GS-Net consists of Geometry Similarity Connection (GSC) modules which exploit Eigen-Graph to group distant points with similar and relevant geometric information, and aggregate features from nearest neighbors in both Euclidean space and Eigenvalue space.
This paper extends, for the first time, transductive Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) approaches to the domain of 3D point cloud classification.
The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction.
Based on this convolution module, we further developed a multi-scale fully convolutional neural network with downsampling and upsampling blocks to enable hierarchical point feature learning.